Ground target tracking-a historical perspective

Airborne sensor platforms such as Joint STARS provide a capability for ground surveillance and monitoring target movements. Because of the high target density and maneuverability, high clutter, low visibility due to terrain masking, etc., ground target tracking presents unique challenges not present in tracking other types of targets. This paper reviews major developments in multi-target tracking over the past four decades and discusses how algorithms developed primarily for tracking air targets can be used for tracking ground targets. The similarities and differences between found and air target tracking are first compared. We then discuss how simple target state estimation algorithms such as Kalman filtering have evolved into more complicated algorithms for tracking maneuvering targets. Similarly, we discuss how association algorithms have progressed from nearest neighbor to joint probabilistic data association (JPDA), multiple hypothesis tracking (MHT), and multi-dimensional assignment. The adequacy of these techniques for tracking ground targets is discussed